Optimum model deployment based on energy consumption

An apparatus comprising:

• a memory;
• and
• at least one processor, wherein the memory and the at least one processor are communicatively coupled, wherein the at least one processor is configured to:
• receive a request from a vehicle for an artificial intelligence (AI) task to be performed by the vehicle,
• identify a plurality of AI models that can each perform the AI task,
• determine an optimum AI model from among the plurality of AI models based on respective energy consumption data of the plurality of AI models and hardware constraints of at least one processor of the vehicle, and
• deploy an instance of the optimum AI model to a software application being executed by the at least one processor of the vehicle.

A computer-readable storage medium comprising instructions, that when read by a processor, cause the processor to perform:

• receiving a request from a vehicle for an artificial intelligence (AI) task to be performed by the vehicle;
• identifying a plurality of AI models that can each perform the AI task;
• determining an optimum AI model from among the plurality of AI models based on respective energy consumption data of the plurality of AI models and hardware constraints of at least one processor of the vehicle;
• and
• deploying an instance of the optimum AI model to a software application being executed by the at least one processor of the vehicle.